Impact of Stain Normalization and Background Filtering on Deep Learning & Transformer Based Models for Ovarian Cancer Histopathology Classification
Bibliographic record
Abstract
Accurate subtype classification of ovarian cancer from H&E histopathology is hindered by stain variability, background artifacts, and class imbalance. We present a controlled study that isolates the effect of preprocessing on downstream performance. Using the UBC-OCEAN dataset, we evaluate two stain normalization methods (Reinhard, Macenko) and an explicit background filter that removes near-white tiles in a$2 \times 2$factorial design. Three architectures ResNet-50, EfficientNetV2-S, and Swin-T are trained with class balanced augmentation and assessed using accuracy, macro-F1, Cohen's$\kappa$, and macro-AUPRC. Excluding near-white tiles consistently improves results across models and normalizations. Under identical background handling, Macenko normalization generally outperforms Reinhard. Swin-T is the strongest backbone overall; the best configuration (Macenko + near-white exclusion + Swin-T) attains 0.9559 accuracy, 0.9534 macro-F1,$0.9401 \kappa$, and 0.9881 macro-AUPRC. These findings demonstrate that simple, explicit preprocessing choices materially affect ovarian cancer subtype classification and should be reported alongside model details to enable reproducibility and fair comparison.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.003 | 0.005 |
| Meta-epidemiology (narrow) | 0.003 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.003 | 0.002 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.002 | 0.002 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".